A Survey on Computational Solutions for Reconstructing Complete Objects by Reassembling Their Fractured Parts
Jiaxin Lu, Yongqing Liang, Huijun Han, Jiacheng Hua, Junfeng Jiang, Xin Li, Qixing Huang
TL;DR
This survey focuses on reconstructing complete objects from fractured parts across diverse domains, detailing the progression from single-piece analysis to multi-piece matching and template-based priors. It synthesizes procedural and deep-learning approaches, highlighting how segmentation, correspondence, and learned shape priors jointly solve reassembly tasks. Key contributions include a structured taxonomy, discussions of symmetry and complete-object priors, and an overview of datasets, metrics, and open-source resources. The work underscores the shift toward learned priors and end-to-end pipelines, while identifying challenges in generalization, data generation, and bridging implicit representations with geometric correspondences, with significant implications for cultural heritage, medicine, and scientific reconstruction.
Abstract
Reconstructing a complete object from its parts is a fundamental problem in many scientific domains. The purpose of this article is to provide a systematic survey on this topic. The reassembly problem requires understanding the attributes of individual pieces and establishing matches between different pieces. Many approaches also model priors of the underlying complete object. Existing approaches are tightly connected problems of shape segmentation, shape matching, and learning shape priors. We provide existing algorithms in this context and emphasize their similarities and differences to general-purpose approaches. We also survey the trends from early non-deep learning approaches to more recent deep learning approaches. In addition to algorithms, this survey will also describe existing datasets, open-source software packages, and applications. To the best of our knowledge, this is the first comprehensive survey on this topic in computer graphics.